Bands

Holds back a prompt that looks like it carries a secret (API keys, tokens, access-key pairs, private keys, passwords) before it reaches the transcript, puts it back in the box, and offers to save the secret as an env var in ~/.zshrc and send $NAME instead. No model calls.

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code, and a plan you approve, then an upgrade, a rewrite or a rebuild with independent proof that the new code behaves like the old. Includes security hardening, a one-page report, specialist agents, and an optional live progress pane (early access).

The usage panel in a sidebar inside Claude Code: this session, today, the last 30 days, projects, top sessions, the day's costliest turns with why each was dear, what pauses cost in cache written again, and insights, with graphs, and, where Claude Burst is installed, the context it really sends by part and Plan Utilisation: how much of the plan's 5-hour and weekly limits is used and which...

Dependency-ordered DAG workflows of Claude Code subagents, with a live DAG pane

Claude proposes, you type: edits become diffs you apply yourself, for deliberate practice.

Remembers which tests passed at the start of the session and warns if any of them now fail.

A links bar above the prompt in Claude Desktop's Code tab: up to 4 pinned links per project or session with favicons, the session's 10 latest links, and a pane of every pinned link. Reads the session transcript; asks a link's own site for its page title and favicon (curl for PNG and ICO icons); opens links with open.

Passagem de bastão entre máquinas (/handoff) e aviso quando um turno longo termina

As tarefas do projeto num TASKS.md: painel, próxima tarefa acima do prompt, e o Claude criando e concluindo tarefas

Painel lateral cyberpunk para o Claude Code (tokens/s, contexto, custo, agentes e ferramentas) e respostas renderizadas em neon: tabelas, codigo, diagramas, LaTeX e tool rows

Pasted images shown as a scrollable shelf above the prompt, even in iTerm2 + tmux; click one to mark it up

Spec Kit progress and usage governance for Claude Code: a phase rail above the prompt, the next command in the prompt hint, the current task on the spinner, a /astrolabe pane, toasts, update buttons, and a status entry with your usage window.

Routes each turn to the cheapest model + effort that fits the task (Haiku 5.5 → Sonnet 5.5 → Opus 5.5 → Fable 5.1) and shows the ladder in a side pane.

A band above the prompt with context size, per-turn cost and the prompt-cache countdown. Past the handoff line it counts down 60 s, writes a handoff file with a fork, runs /clear and resumes in the new conversation; a new conversation lists unclaimed handoff files, press 1 to resume.

Ambient language learning. Hooks weave vocabulary into ordinary Claude Code sessions — stale items you are forgetting, a small budget of new terms drawn from the work itself, and anything you use unprompted recorded rather than taught back at you. The ledger is a markdown file you own, written by a CLI rather than by hand.

Keeps the follow-ups Claude suggests in one backlog shared by every session, and a checklist Claude keeps for multi-step work in each session, each with a footer button and a pane

Otto, a blue octopus, forecasts your context window on one line above the prompt, in the Claude Code desktop app, and in text in the terminal: weather scaled to auto-compact with what fills the context on hover, the tokens each recent prompt added, and your 5-hour and 7-day limits with a pace projection. Labels in English or French. Fork of Anthropic's Token Weather (Apache-2.0).

Live workflow map: one row above the prompt (what is running, what is next, segmented progress) that expands into a card graph of parallel steps, plus a full stage-by-stage view and a flowchart of parallel groups, with your mid-plan interjections clearly marked (whether they were recorded, what each one changed shown on the plan, the plan before it, a timeline), an honest time-left range...

A pane listing each prompt's token usage and its cost at standard API (Enterprise usage) rates; /token-panel turns it on and off

Shows every live Claude Code session as a card in a side pane: title, status, current tool, git branch, model, context use and a last-turn recap. No tmux or daemon needed; in tmux a card's hotkey jumps to that session's pane

claudebar as a mod: an interactive band with git, model, effort, context, rate limits, cache, tools and agents, plus detail panes, alerts and history

Panel de consumo de tu suscripción con historial, predicción, tokens, precio y consumo por turno, modo ahorro automático y una mascota que reacciona a lo que hace Claude y a sus subagentes

Agents info Mod (Claude Code 2.1.287, Mods API in early access): starting agent, timeline of agents per prompt (new, resumed, forked), resolved model and effort of each, tokens per agent × model × effort, 5 h / 7 day limits with forecast, alerts. Read-only: alters and blocks nothing.

Your Codex pet, living above the Claude Code prompt: it works while Claude works, waits when you are needed, and celebrates when a turn is done.